Ling Mini Base 2.0 15T needs about 11.2 GB of memory at Q4_K_M (a 10.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 18 quants, from 0.1 GB to 14.1 GB (Q6_K).
Ling Mini Base 2.0 15T is a 17.1B-parameter Ling model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 18 quant files, from 0.1 GB to 14.1 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 0.8 GB | Fits | Get file → | |
| Q2_K | 6.4 GB | 7.0 GB | Fits | Get file → | |
| IQ3_XXS | 6.7 GB | 7.4 GB | Tight | Get file → | |
| IQ3_XS | 7.1 GB | 7.8 GB | Tight | Get file → | |
| IQ3_S | 7.5 GB | 8.2 GB | Too big | Get file → | |
| Q3_K_S | 7.5 GB | 8.2 GB | Too big | Get file → | |
| IQ3_M | 7.6 GB | 8.3 GB | Too big | Get file → | |
| Q3_K_M | 8.3 GB | 8.9 GB | Too big | Get file → | |
| Q3_K_L | 8.9 GB | 9.6 GB | Too big | Get file → | |
| IQ4_XS | 9.2 GB | 9.9 GB | Too big | Get file → | |
| IQ4_NL | 9.7 GB | 10.4 GB | Too big | Get file → | |
| Q4_0 | 9.8 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_S | 9.8 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_M | 10.4 GB | 11.1 GB | Too big | Get file → | |
| Q4_1 | 10.8 GB | 11.5 GB | Too big | Get file → | |
| Q5_K_S | 11.8 GB | 12.5 GB | Too big | Get file → | |
| Q5_K_M | 12.2 GB | 12.8 GB | Too big | Get file → | |
| Q6_K | 14.1 GB | 14.7 GB | Too big | Get file → |
What GPU do you need for Ling Mini Base 2.0 15T?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XS (7.1 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (10.8 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (14.1 GB file, about 14.9 GB in use).
Which Ling Mini Base 2.0 15T quant should you choose?
Q4_K_M is the usual starting point for Ling Mini Base 2.0 15T: it balances file size and quality well. Here it is a 10.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ling Mini Base 2.0 15T
How much VRAM does Ling Mini Base 2.0 15T need?
About 11.2 GB at Q4_K_M with an 8K context window. That is the 10.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Ling Mini Base 2.0 15T on an 8 GB GPU?
Yes, with IQ3_XS: the 7.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Ling Mini Base 2.0 15T GGUF?
It depends on the quant: file is 0.1 GB, Q2_K is 6.4 GB, IQ3_XXS is 6.7 GB, IQ3_XS is 7.1 GB, IQ3_S is 7.5 GB, Q3_K_S is 7.5 GB and 12 more.
What context length does Ling Mini Base 2.0 15T support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.2 GB at 4K.
Where can I download Ling Mini Base 2.0 15T GGUF?
The files are on Hugging Face in the mradermacher/Ling-mini-base-2.0-15T-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Ling Mini Base 2.0 15T use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.